hn · Show HN · 11-02 17:16 50 分 ← 返回列表

Show HN: Subvocal – Talk to your computer without making noise

原文链接 ↗ ·aarushyadav

Hi HN, we're Aarush and Arnav from The Subvocal Company (YC F26). We’re building smart glasses that let you talk to your computer without talking out loud. You can mouth words silently and discreetly and the glasses decode them to text at the speed of speech. Here's a video of Dave from YC trying it out: https://www.youtube.com/watch?v=9QdX1eObVYI Arnav and I were studying CS at Georgia Tech at the beginning of the year, with no experience in silent speech or sensing. We were both AI-native bu

五维评分

付费意愿

需求真实度

个人可落地

竞争空间

新鲜度

AI 分析

痛点：现有语音输入工具在图书馆、办公室等安静或公共场合无法使用，用户需要不发声也能高速输入文字。

目标用户：需要高频语音输入的知识工作者、程序员、学生，尤其在安静/公共场景；以及智能眼镜用户。

证据：What bugged us was not being able to use these tools in the library (or an office) or in public. We were both AI-native builders and power users of Wispr Flow.

变现：硬件眼镜销售 + 订阅制解码/软件服务；独立开发者可考虑做垂直场景的静音输入 SDK/API、插件或需求验证型工具。

MVP：2周不适合复刻硬件。可先做需求验证落地页+waitlist，并用摄像头口型+麦克风低音量识别做仅支持少量指令/短语的软件原型，验证安静场景下的付费意愿。

竞品：Wispr Flow、MIT AlterEgo、Meta Ray-Ban smart glasses

摘要：YC F26 团队发布 Subvocal 智能眼镜，通过 RF 感知无声口型并解码为文本，解决 Wispr Flow 等语音输入在图书馆、办公室、公共场合不能用的问题。HN 获 57 分 27 评论，团队从 EMG 转向 RF，说明需求真实但硬件、传感与解码门槛高，独立开发者难以直接复刻。